Theory of Architecture as the Maestro Organising AI Text-to-Image Prompts

Engineering notes

Key topics: autonomous driving. See the paper for implementation details and experimental results.

Chinese explanation / 中文解读

中文解读待补充：本站会优先为端到端自动驾驶、BEV感知、3D目标检测、轨迹预测、路径规划、LiDAR感知等高价值论文补充中文说明。

Original abstract

In the wake of the Fifth Industrial Revolution, artificial intelligence (AI) has become a disruptive force in architectural design processes. One AI technique is text-to-image, which generates visual representations from textual descriptions. This research questions how architects and students organise the text-to-image prompts. Unfortunately, AI images have neglected the basic principles of architectural theories. The problem explored here is whether AI-generated images truly reflect architectural theory or replicate styles without deep understanding. This research, therefore, aims to propose a chart of semantic textual models, including keywords of theories of architecture, to organise the text-to-image prompts. To achieve this aim, the article followed scientific methodology, began with a literature review, and then analysed previous readings that highlighted this gap and proposed solutions. Through three AI platforms, the research followed an experimental method, injecting five architectural theories into AI prompts to compare images before and after. As a result, the images (after) became more realistic, expressing more clearly the trend's characteristics, and conveying symbolic meanings. The conclusion is that AI architectural images must have a maestro to organise prompts. This maestro is the 'Theory of Architecture', which is expected to bridge the gap between AI's ultimate imagination and the authentic principles of design trends.

Links and sources

Comments